Imaging Reconstruction Research Articles

Magnetic resonance imaging in granular flows: An overview of recent advances

In this review we explore the recent developments in the use of Magnetic Resonance Imaging (MRI) for studying granular flows. While MRI has been a valuable tool in this field for the past 40 years, recent advances in imaging hardware, reconstruction software and particles synthesis have significantly enhanced its capabilities. This article provides an overview of the current challenges of MRI and progress in the field of granular media, and gives a perspective of the possible future developments in the field.

Computed Tomographic Analysis of Position of Mandibular Canal and Mandibular Foramen in Patients with Mandibular Asymmetry.

Mandibular osteotomies in facial asymmetry are complicated by the abnormal position and course of inferior alveolar nerve. This manuscript aims to evaluate the possible variations in the preoperative positions of mandibular canal and mandibular foramen in patients with mandibular asymmetry due to condylar hyperplasia or condylar hypoplasia. This study included 15 patients with mandibular asymmetry due to condylar hyperplasia or condylar hypoplasia for which bilateral sagittal split osteotomy (BSSO) was performed as a corrective procedure. The presence/absence and extent of postoperative neurosensory deficiency was recorded subjectively and objectively. The measurements were done using multiplanar reconstruction (MPR) of three-dimensional radiographic imaging and were compared to normal subjects. The results revealed that the mandibular canal was closer to the buccal cortex on the affected side and the inferior border on both sides in the region of second molar in condylar hyperplasia. In condylar hypoplasia, the canal was nearer to the inferior border and the alveolar crest in relation to second and third molars respectively on the affected and contralateral sides.The mandibular foramen was also more superior to the occlusal plane on both sides in both condylar hyperplasia and hypoplasia. Based on the study outcomes, the authors propose that assessment of the positions of mandibular canal and mandibular foramen is crucial to avoid postoperative neurosensory deficiencies.

Retraction: Magnetic resonance imaging reconstruction algorithm under complex convolutional neural network in diagnosis and prognosis of cerebral infarction.

Retraction: Magnetic resonance imaging reconstruction algorithm under complex convolutional neural network in diagnosis and prognosis of cerebral infarction.

A circuit suppressing retinal drive to the optokinetic system during fast image motion

Optokinetic nystagmus (OKN) assists stabilization of the retinal image during head rotation. OKN is driven by ON direction selective retinal ganglion cells (ON DSGCs), which encode both the direction and speed of global retinal slip. The synaptic circuits responsible for the direction selectivity of ON DSGCs are well understood, but those sculpting their slow-speed preference remain enigmatic. Here, we probe this mechanism in mouse retina through patch clamp recordings, functional imaging, genetic manipulation, and electron microscopic reconstructions. We confirm earlier evidence that feedforward glycinergic inhibition is the main suppressor of ON DSGC responses to fast motion, and reveal the source for this inhibition—the VGluT3 amacrine cell, a dual neurotransmitter, excitatory/inhibitory interneuron. Together, our results identify a role for VGluT3 cells in limiting the speed range of OKN. More broadly, they suggest VGluT3 cells shape the response of many retinal cell types to fast motion, suppressing it in some while enhancing it in others.

Fourier Single-Pixel Imaging Based on Online Modulation Pattern Binarization

Down-sampling Fourier single-pixel imaging is typically achieved by truncating the Fourier spectrum, where exclusively the low-frequency Fourier coefficients are extracted while discarding the high-frequency components. However, the truncation of the Fourier spectrum can lead to an undesired ringing effect in the reconstructed result. Moreover, the original Fourier single-pixel imaging necessitated grayscale Fourier basis patterns for illumination. This requirement limits imaging speed because digital micromirror devices (DMDs) generate grayscale patterns at a lower refresh rate. In order to solve the above problem, a fast and high-quality Fourier single-pixel imaging reconstruction method is proposed in the paper. In the method, the threshold binarization of the Fourier base pattern is performed online to improve the DMD refresh rate, and the reconstruction quality of Fourier single-pixel imaging at a low-sampling rate is improved by generating an adversarial network. This method enables fast reconstruction of target images with higher quality despite low-sampling rates. Compared with conventional Fourier single-pixel imaging, numerical simulation and experimentation demonstrate the effectiveness of the proposed method. Notably, this method is particularly significant for fast Fourier single-pixel imaging applications.

Intravoxel incoherent motion magnetic resonance imaging reconstruction from highly under-sampled diffusion-weighted PROPELLER acquisition data via physics-informed residual feedback unrolled network

Objective. The acquisition of diffusion-weighted images for intravoxel incoherent motion (IVIM) imaging is time consuming. This work aims to accelerate the scan through a highly under-sampling diffusion-weighted turbo spin echo PROPELLER (DW-TSE-PROPELLER) scheme and to develop a reconstruction method for accurate IVIM parameter mapping from the under-sampled data. Approach . The proposed under-sampling DW-TSE-PROPELLER scheme for IVIM imaging is that a few blades per b-value are acquired and rotated along the b-value dimension to cover high-frequency information. A physics-informed residual feedback unrolled network (PIRFU-Net) is proposed to directly estimate distortion-free and artifact-free IVIM parametric maps (i.e., the perfusion-free diffusion coefficient D and the perfusion fraction f) from highly under-sampled DW-TSE-PROPELLER data. PIRFU-Net used an unrolled convolution network to explore data redundancy in the k-q space to remove under-sampling artifacts. An empirical IVIM physical constraint was incorporated into the network to ensure that the signal evolution curves along the b-value follow a bi-exponential decay. The residual between the realistic and estimated measurements was fed into the network to refine the parametric maps. Meanwhile, the use of synthetic training data eliminated the need for genuine DW-TSE-PROPELLER data. Main results . The experimental results show that the DW-TSE-PROPELLER acquisition was six times faster than full k-space coverage PROPELLER acquisition and within a clinically acceptable time. Compared with the state-of-the-art methods, the distortion-free D and f maps estimated by PIRFU-Net were more accurate and had better-preserved tissue boundaries on a simulated human brain and realistic phantom/rat brain/human brain data. Significance . Our proposed method greatly accelerates IVIM imaging. It is capable of directly and simultaneously reconstructing distortion-free, artifact-free, and accurate D and f maps from six-fold under-sampled DW-TSE-PROPELLER data.

Deep learning-based reconstruction for canine brain magnetic resonance imaging could improve image quality while reducing scan time.

Optimal magnetic resonance imaging (MRI) quality and shorter scan time are challenging to achieve in veterinary practices. Recently, deep learning-based reconstruction (DLR) has been proposed for ideal image quality. We hypothesized that DLR-based MRI will improve brain imaging quality and reduce scan time. This prospective, methods comparison study compared the MR image denoising performances of DLR and conventional methods, with the aim of reducing scan time and improving canine brain image quality. Transverse T2-weighted and fluid-attenuated inversion recovery (FLAIR) sequences of the brain were performed in 12 clinically healthy beagle dogs. Different numbers of excitations (NEX) were used to obtain the image groups NEX4, NEX2, and NEX1. DLR was applied to NEX2 and NEX1 to obtain NEX2DL and NEX1DL . The scan times were recorded, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated for quantitative analysis. Five blinded veterinarians assessed the overall quality, contrast, and perceived SNR on four-point Likert scales. Quantitative and qualitative values were compared among the five groups. Compared with NEX4, NEX2 and NEX1 reduced scan time by 50% and 75%, respectively. The mean SNR and CNR of NEX2DL and NEX1DL were significantly superior to those of NEX4, NEX2, and NEX1 (P<0.05). In all image quality indices, DLR-applied images for both T2-weighted and FLAIR images were significantly higher than NEX4 and NEX2DL had significantly better quality than NEX1DL for FLAIR (P<0.05). Findings indicated that DLR reduced scan time and improved image quality compared with conventional MRI images in a sample of clinically healthy beagles.

High-throughput MALDI-MSI metabolite analysis of plant tissue microarrays.

A novel metabolomics analysis technique, termed matrix-assisted laser desorption/ionization mass spectrometry imaging-based plant tissue microarray (MALDI-MSI-PTMA), was successfully developed for high-throughput metabolite detection and imaging from plant tissues. This technique completely overcomes the disadvantage that metabolites cannot be accessible on anintact plant tissue due to the limitations of the special structures of plant cells (e.g. epicuticular wax, cuticle and cell wall) through homogenization of plant tissues, preparation of PTMA moulds and matrix spraying of PTMA sections. Our study shows several properties of MALDI-MSI-PTMA, including no need of sample separation and enrichment, high-throughput metabolite detection and imaging (>1000 samples per day), high-stability mass spectrometry data acquisition and imaging reconstruction and high reproducibility of data. This novel technique was successfully used to quickly evaluate the effects of two plant growth regulator treatments (i.e. 6-benzylaminopurine and N-phenyl-N'-1,2,3-thiadiazol-5-ylurea) on endogenous metabolite expression in plant tissue culture specimens of Dracocephalum rupestre Hance (D.rupestre). Intra-day and inter-day evaluations indicated that the metabolite data detected on PTMA sections had good reproducibility and stability. A total of 312 metabolite ion signals inleaves tissues of D. rupestre were detected, of which 228 metabolite ion signals were identified, they were composed of 122 primary metabolites, 90 secondary metabolites and 16 identified metabolites of unknown classification. The results demonstrated the advantages of MALDI-MSI-PTMA technique for enhancing the overall detection ability of metabolites in plant tissues, indicating that MALDI-MSI-PTMA has the potential to become a powerful routine practice for high-throughput metabolite study in plant science.

Applicability Evaluation of Full-Reference Image Quality Assessment Methods for Computed Tomography Images

Image quality assessments (IQA) are an important task for providing appropriate medical care. Full-reference IQA (FR-IQA) methods, such as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), are often used to evaluate imaging conditions, reconstruction conditions, and image processing algorithms, including noise reduction and super-resolution technology. However, these IQA methods may be inapplicable for medical images because they were designed for natural images. Therefore, this study aimed to investigate the correlation between objective assessment by some FR-IQA methods and human subjective assessment for computed tomography (CT) images. For evaluation, 210 distorted images were created from six original images using two types of degradation: noise and blur. We employed nine widely used FR-IQA methods for natural images: PSNR, SSIM, feature similarity (FSIM), information fidelity criterion (IFC), visual information fidelity (VIF), noise quality measure (NQM), visual signal-to-noise ratio (VSNR), multi-scale SSIM (MSSSIM), and information content-weighted SSIM (IWSSIM). Six observers performed subjective assessments using the double stimulus continuous quality scale (DSCQS) method. The performance of IQA methods was quantified using Pearson’s linear correlation coefficient (PLCC), Spearman rank order correlation coefficient (SROCC), and root-mean-square error (RMSE). Nine FR-IQA methods developed for natural images were all strongly correlated with the subjective assessment (PLCC and SROCC > 0.8), indicating that these methods can apply to CT images. Particularly, VIF had the best values for all three items, PLCC, SROCC, and RMSE. These results suggest that VIF provides the most accurate alternative measure to subjective assessments for CT images.

WKGM: weighted k-space generative model for parallel imaging reconstruction.

Deep learning based parallel imaging (PI) has made great progress in recent years to accelerate MRI. Nevertheless, it still has some limitations: for example, the robustness and flexibility of existing methods are greatly deficient. In this work, we propose a method to explore the k-space domain learning via robust generative modeling for flexible calibrationless PI reconstruction, coined the weighted k-space generative model (WKGM). Specifically, WKGM is a generalized k-space domain model, where the k-space weighting technology and high-dimensional space augmentation design are efficiently incorporated for score-based generative model training, resulting in good and robust reconstructions. In addition, WKGM is flexible and thus can be synergistically combined with various traditional k-space PI models, which can make full use of the correlation between multi-coil data and realize calibrationless PI. Even though our model was trained on only 500 images, experimental results with varying sampling patterns and acceleration factors demonstrate that WKGM can attain state-of-the-art reconstruction results with the well learned k-space generative prior.

Bayesian reconstruction of magnetic resonance images using Gaussian processes

A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based reconstruction. Here, we propose and demonstrate a Bayesian method to build statistical libraries of magnetic resonance (MR) images in k-space and use these libraries to identify optimal subsampling paths and reconstruction processes. Specifically, we compute a multivariate normal distribution based upon Gaussian processes using a publicly available library of T1-weighted images of healthy brains. We combine this library with physics-informed envelope functions to only retain meaningful correlations in k-space. This covariance function is then used to select a series of ring-shaped subsampling paths using Bayesian optimization such that they optimally explore space while remaining practically realizable in commercial MRI systems. Combining optimized subsampling paths found for a range of images, we compute a generalized sampling path that, when used for novel images, produces superlative structural similarity and error in comparison to previously reported reconstruction processes (i.e. 96.3% structural similarity and < 0.003 normalized mean squared error from sampling only 12.5% of the k-space data). Finally, we use this reconstruction process on pathological data without retraining to show that reconstructed images are clinically useful for stroke identification. Since the model trained on images of healthy brains could be directly used for predictions in pathological brains without retraining, it shows the inherent transferability of this approach and opens doors to its widespread use.

Genetic reporter for live tracing fluid flow forces during cell fate segregation in mouse blastocyst development.

Mechanical forces are known to be important in mammalian blastocyst formation; however, due to limited tools, specific force inputs and how they relay to first cell fate control of inner cell mass (ICM) and/or trophectoderm (TE) remain elusive. Combining in toto live imaging and various perturbation experiments, we demonstrate and measure fluid flow forces existing in the mouse blastocyst cavity and identify Klf2(Krüppel-like factor 2) as a fluid force reporter with force-responsive enhancers. Long-term live imaging and lineage reconstructions reveal that blastomeres subject to higher fluid flow forces adopt ICM cell fates. These are reinforced by internal ferrofluid-induced flow force assays. We also utilize exvivo fluid flow force mimicking and pharmacological perturbations to confirm mechanosensing specificity. Together, we report a genetically encoded reporter for continuously monitoring fluid flow forces and cell fate decisions and provide a live imaging framework to infer force information enriched lineage landscape during development. VIDEO ABSTRACT.

Measurement Technologies of Light Field Camera: An Overview.

Visual measurement methods are extensively used in various fields, such as aerospace, biomedicine, agricultural production, and social life, owing to their advantages of high speed, high accuracy, and non-contact. However, traditional camera-based measurement systems, relying on the pinhole imaging model, face challenges in achieving three-dimensional measurements using a single camera by one shot. Moreover, traditional visual systems struggle to meet the requirements of high precision, efficiency, and compact size simultaneously. With the development of light field theory, the light field camera has garnered significant attention as a novel measurement method. Due to its special structure, the light field camera enables high-precision three-dimensional measurements with a single camera through only one shot. This paper presents a comprehensive overview of light field camera measurement technologies, including the imaging principles, calibration methods, reconstruction algorithms, and measurement applications. Additionally, we explored future research directions and the potential application prospects of the light field camera.

Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder.

The COVID-19 pandemic has underscored the urgent need for rapid and accurate diagnosis facilitated by artificial intelligence (AI), particularly in computer-aided diagnosis using medical imaging. However, this context presents two notable challenges: high diagnostic accuracy demand and limited availability of medical data for training AI models. To address these issues, we proposed the implementation of a Masked AutoEncoder (MAE), an innovative self-supervised learning approach, for classifying 2D Chest X-ray images. Our approach involved performing imaging reconstruction using a Vision Transformer (ViT) model as the feature encoder, paired with a custom-defined decoder. Additionally, we fine-tuned the pretrained ViT encoder using a labeled medical dataset, serving as the backbone. To evaluate our approach, we conducted a comparative analysis of three distinct training methods: training from scratch, transfer learning, and MAE-based training, all employing COVID-19 chest X-ray images. The results demonstrate that MAE-based training produces superior performance, achieving an accuracy of 0.985 and an AUC of 0.9957. We explored the mask ratio influence on MAE and found ratio = 0.4 shows the best performance. Furthermore, we illustrate that MAE exhibits remarkable efficiency when applied to labeled data, delivering comparable performance to utilizing only 30% of the original training dataset. Overall, our findings highlight the significant performance enhancement achieved by using MAE, particularly when working with limited datasets. This approach holds profound implications for future disease diagnosis, especially in scenarios where imaging information is scarce.

CSA: A Channel-Separated Attention Module for Enhancing MRI Reconstruction.

Channel attention mechanisms have been proven to effectively enhance network performance in various visual tasks, including the Magnetic Resonance Imaging (MRI) reconstruction task. Channel attention mechanisms typically involve channel dimensionality reduction and cross-channel interaction operations to achieve complexity reduction and generate more effective weights of channels. However, the operations may negatively impact MRI reconstruction performance since it was found that there is no discernible correlation between adjacent channels and the low information value in some feature maps. Therefore, we proposed the Channel-Separated Attention (CSA) module tailored for MRI reconstruction networks. Each layer of the CSA module avoids compressing channels, thereby allowing for lossless information transmission. Additionally, we employed the Hadamard product to realize that each channel's importance weight was generated solely based on itself, avoiding cross-channel interaction and reducing the computational complexity. We replaced the original channel attention module with the CSA module in an advanced MRI reconstruction network and noticed that CSA module achieved superior reconstruction performance with fewer parameters. Furthermore, we conducted comparative experiments with state-of-the-art channel attention modules on an identical network backbone, CSA module achieved competitive reconstruction outcomes with only approximately 1.036% parameters of the Squeeze-and-Excitation (SE) module. Overall, the CSA module makes an optimal trade-off between complexity and reconstruction quality to efficiently and effectively enhance MRI reconstruction. The code is available at https://github.com/smd1997/CSA-Net.

Low-rank tensor assisted K-space generative model for parallel imaging reconstruction

Although recent deep learning methods, especially generative models, have shown good performance in magnetic resonance imaging, there is still much room for improvement. Considering that the sample number and internal dimension in score-based generative model have key influence on estimating the gradients of data distribution, we present a new idea for parallel imaging reconstruction, named low-rank tensor assisted k-space generative model (LR-KGM). It means that we transform low-rank information into high-dimensional prior information for learning. More specifically, the multi-channel data is constructed into a large Hankel matrix to reduce the number of training samples, which is subsequently collapsed into a tensor for the stage of prior learning. In the testing phase, the low-rank rotation strategy is utilized to impose low-rank constraints on the output tensors of the generative network. Furthermore, we alternate the reconstruction between traditional generative iterations and low-rank high-dimensional tensor iterations. Experimental comparisons with the state-of-the-arts demonstrated that the proposed LR-KGM method achieved better performance.

Improved Simultaneous Multi-slice imaging with Composition of k-space Interpolations (SMS-COOKIE) for myocardial T1 mapping.

The aim of this study is to develop and evaluate a regularized Simultaneous Multi-Slice (SMS) reconstruction method for improved Cardiac Magnetic Resonance Imaging (CMR). The proposed reconstruction method, SMS with COmpOsition of k-space IntErpolations (SMS-COOKIE) combines the advantages of Iterative Self-consistent Parallel Imaging Reconstruction (SPIRiT) and split slice-Generalized Autocalibrating Partially Parallel Acquisitions (GRAPPA), while allowing regularization for further noise reduction. The proposed SMS-COOKIE was implemented with and without regularization, and validated using a Saturation Pulse-Prepared Heart rate Independent inversion REcovery (SAPPHIRE) myocardial T1 mapping sequence. The performance of the proposed reconstruction method was compared to ReadOut (RO)-SENSE-GRAPPA and split slice-GRAPPA, on both retrospectively and prospectively three-fold SMS-accelerated data with an additional two-fold in-plane acceleration. All SMS reconstruction methods yielded similar T1 values compared to single band imaging. SMS-COOKIE showed lower spatial variability in myocardial T1 with significant improvement over RO-SENSE-GRAPPA and split slice-GRAPPA (P < 10-4). The proposed method with additional locally low rank (LLR) regularization reduced the spatial variability, again with significant improvement over RO-SENSE-GRAPPA and split slice-GRAPPA (P < 10-4). In conclusion, improved reconstruction quality was achieved with the proposed SMS-COOKIE, which also provided lower spatial variability with significant improvement over split slice-GRAPPA.

Dynamic residual Kaczmarz method for noise reducing reconstruction in magnetic particle imaging

Objective. Here, we propose a dynamic residual Kaczmarz (DRK) method as an improved reconstruction method for magnetic particle imaging (MPI) to achieve a better reconstruction quality from high-noise signals. Approach. Based on the Kaczmarz (KZ) method, we introduced a residual vector to select parts of the low-noise equations for reconstruction. In each iteration, a low-noise subset was formulated based on the residual vector. Thus, the reconstruction converged to an accurate result with less noise. Main Results. To evaluate the performance of the proposed method, it was compared with classical Kaczmarz-type methods and state-of-the-art regularization models. The numerical simulation results demonstrate that the DRK method can achieve better reconstruction quality than all other comparison methods at similar noise levels. It can acquire a signal-to-background ratio (SBR) that is five times higher than that of classical Kaczmarz-type methods at a 5 dB noise level. Furthermore, the DRK method can acquire up to 0.7 structural similarity (SSIM) indicators at a 5 dB noise level when combined with the non-negative fused Least absolute shrinkage and selection operator (LASSO) regularization model. In addition, a real experiment based on the OpenMPI data set validated that the proposed DRK method can be applied to real data and perform well. Significance. The experimental results demonstrate that the proposed DRK method can significantly improve the reconstruction quality of MPI when the signals contain high noise. It has the potential to be applied to MPI instruments that contain high signal noise, such as human-sized MPI instruments. It is beneficial for expanding the biomedical applications of MPI technology.

Difference between planned and delivered radiotherapy dose to the internal mammary nodes in high-risk breast cancer patients.

Chest wall movement during radiotherapy can impact the delivered dose to the internal mammary nodes (IMN) in high-risk breast cancer patients. Using portal imaging and dose reconstruction we aimed to examine the delivered IMN dose coverage. Cine MV images were recorded for 39 breast cancer patients treated with daily image-guided radiotherapy (IGRT) in deep-inspiration breath-hold (DIBH). On the final frame of each cine MV recording the chest wall was matched with the Digitally Reconstructed Radiograph (DRR) from the treatment plan. The geometrical chest wall error was determined in the imager-plane perpendicular to the cranio-caudal direction, rounded to integer millimeters, and binned. For each 1mm bin, an isocenter-shifted treatment plan was recalculated assuming that the projected error observed in the cine MV image was caused by anterior-posterior chest wall movement in the IMN region. A weighted plan sum yielded the IMN clinical target volume receiving at least 90% dose (V90_CTVn_IMN). The mean number of cine MV observations per patient was 36 (range 26-55). Most patients (67%) had on average a posterior chest wall position at treatment compared to planned. This translated into a change in the delivered median V90_CTVn_IMN of -0.7% (range, -11.9-2.9%; p<0.001). The V90_CTVn_IMN reduction wasgreater than9% in three patients. No clinically relevant differences were found for the mean lung dose or mean heart dose. Using cine MV images, we found that the delivered V90_CTVn_IMN was significantly lower than planned. In 8% of the patients, the V90_CTVn_IMN reduction exceeded 9%.

Extended aperture image reconstruction for plane-wave imaging

B-mode images undergo degradation in the boundary region because of the limited number of elements in the ultrasound probe. Herein, a deep learning-based extended aperture image reconstruction method is proposed to reconstruct a B-mode image with an enhanced boundary region. The proposed network can reconstruct an image using pre-beamformed raw data received from the half-aperture of the probe. To generate a high-quality training target without degradation in the boundary region, the target data were acquired using the full-aperture. Training data were acquired from an experimental study using a tissue-mimicking phantom, vascular phantom, and simulation of random point scatterers. Compared with plane-wave images from delay and sum beamforming, the proposed extended aperture image reconstruction method achieves improvement at the boundary region in terms of the multi-scale structure of similarity and peak signal-to-noise ratio by 8% and 4.10 dB in resolution evaluation phantom, 7% and 3.15 dB in contrast speckle phantom, and 5% and 3 dB in in vivo study of carotid artery imaging. The findings in this study prove the feasibility of a deep learning-based extended aperture image reconstruction method for boundary region improvement.